| 山根 弘樹 | M, 2回目発表 | コンピューティング・アーキテクチャ | 中島 康彦, 池田 和司, 中田 尚, TRAN THI HONG, 張 任遠 |
|
title: Development and Evaluation of Letter Reproduction System using Cellular Neural Network and Oxide Semiconductor Synapses
abstract: We develop a neural network using oxide semiconductor synapse and evaluate character reproducibility. An amorphous metal oxide semiconductor device is used for the synapse element, and characteristic deterioration is used for a learning rule called Hebuan learning. First, we explain the architecture and operation of the cellular neural network, simulate it and evaluate the performance. language of the presentation: Japanese | |||
| 譽田 実希子 | M, 2回目発表 | 数理情報学 | 池田 和司, 向川 康博, 久保 孝富, 佐々木 博昭 |
|
TItle: Analysis of Finless Porpoise Hunting Behavior.
Abstract: Finless porpoise, Neophocaena asiaeorintalis, is small-toothed whale distributed in coastal water in Japan, China and Korea. They are not gregarious animal and it is rare for them to make large flocks. However, they sometimes form large group to hunt fish. Their forming strategy affecting is unknown. We try to analysis of finless porpoise hunting behavior. We analyzed the behavior of Finless Porpoise from the movies. Language of the presentation: Japanese | |||
| LAO BRYAN TSANG | D, 中間発表 | 数理情報学 | 池田 和司, 中村 哲, Nishanth Koganti |
|
title: An Analysis of Expert Therapy in the Sit-to-Stand Movement
abstract: Sit-to-stand (STS) movement is an essential prerequisite to most activities of daily living, and its difficulty often affects the quality of life of elderly people. Treatment is often performed by physical therapists by inducing a standing strategy that is beneficial to the patient. However, with the shortage of health care services in super-aging societies, improvements to existing therapy methods have become necessary. Our goal is to characterize the mechanisms of expert-induced standing strategies and supplement the existing treatments. In this talk, we focus on quantifying STS strategies using muscle synergies, a functional representation of neural command. By analyzing its temporal parameters, we identify distinct patterns among natural and expert-guided standing conditions. Specifically, we identify changes induced by the expert on natural strategies. language of the presentation: English | |||
| 高橋 晴太郎 | M, 2回目発表 | 数理情報学 | 池田 和司, 中村 哲, 吉野 幸一郎, 久保 孝富, 佐々木 博昭 |